Skip to main content
Glama
AnkleBreaker-Studio

Unity MCP Server

by AnkleBreaker-Studio
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

unity_graphics_game_capture

Render one Unity camera to an inline PNG, excluding Game View composition and overlay UI, for clean captures at custom sizes.

Instructions

Render one camera to inline PNG, without Game View composition or overlay UI. Whole-pixel sizes within device limits, at most 33554432 pixels.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
portNoUnity instance port (from unity_select_instance). Always include it when multiple instances run.
widthNoImage width in pixels (default: 512)
heightNoImage height in pixels (default: 512)
cameraNameNoActive object's name/path; omitted: Camera.main. Missing explicit camera is an error.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv2.36.0
    • changedInput schema / properties / cameraName / description
      Previous value: -"Name of camera to use (default: Camera.main / MainCamera tag)"New value: +"Active object's name/path; omitted: Camera.main. Missing explicit camera is an error."
    • addedInput schema / properties / height / maximum
      Added value: +8192
    • addedInput schema / properties / height / minimum
      Added value: +1
    • addedInput schema / properties / width / maximum
      Added value: +8192
    • addedInput schema / properties / width / minimum
      Added value: +1
  2. Changed1 schema field changedv2.35.6
    • changedInput schema / properties / port / description
      Previous value: -"Target Unity instance port for parallel-safe routing. Get this from unity_select_instance. When working with multiple Unity instances, ALWAYS include this parameter."New value: +"Unity instance port (from unity_select_instance). Always include it when multiple instances run."
  3. Addedv2.28.1

TDQS

B3.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full burden. It usefully discloses that output is an inline PNG (returned data, not a saved file), that Game View composition and overlay UI are excluded, and the aggregate 33554432-pixel ceiling. It does not, however, mention failure behavior, permissions, or timing constraints, leaving notable gaps for a capture tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences with no filler, front-loading the core action before the composition caveat. It could be marginally tighter, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description identifies the return form (inline PNG) and the key rendering constraint, and the schema covers the camera default (Camera.main) and error case. Given the absence of annotations, more behavioral detail would help, but an agent has enough to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so width/height/cameraName/port semantics are already documented, setting the baseline at 3. The description does add one thing the schema cannot express: a combined total-pixel limit (33554432) that constrains legal width×height combinations, since each axis alone may reach 8192.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Render one camera to inline PNG") and adds the distinguishing scope note "without Game View composition or overlay UI," which implicitly separates it from the screenshot siblings. It does not name the closest sibling (unity_screenshot_game) outright, so the agent must infer the distinction rather than being routed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use, when-not-to-use, or named alternative. The implicit contrast with Game View composition hints at a use case, but with siblings like unity_screenshot_game and unity_graphics_scene_capture present, the definition leaves the selection decision entirely to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools